Skip to content

Releases: marcpinet/neuralnetlib

neuralnetlib 3.0.8

10 Nov 01:37
d9852ba
Compare
Choose a tag to compare
  • docs: update dinosaurs example
  • perf(Adam/RNN): better gradient handling
  • ci: bump version to 3.0.8

neuralnetlib 3.0.7

10 Nov 00:45
9b3d806
Compare
Choose a tag to compare
  • fix(attention): correct gradient computation in dot-product attention
  • fix(RNN): global clipping instead of individual
  • docs: update readme
  • ci: bump version to 3.0.7

neuralnetlib 3.0.6

09 Nov 23:10
40ab4f2
Compare
Choose a tag to compare
  • fix: GRU to Model exceptions
  • ci: bump version to 3.0.6

neuralnetlib 3.0.5

09 Nov 23:07
014e044
Compare
Choose a tag to compare
  • feat: add GRU layer
  • ci: bump version to 3.0.5

neuralnetlib 3.0.4

09 Nov 18:59
6ddbca0
Compare
Choose a tag to compare
  • feat: add sparse cce
  • fix: f1score, precision, recall for bc
  • refactor: better weights and biases init
  • fix(Adam): limit cases and gradient clipping
  • docs: update examples
  • feat: improve dropout and add new regularizers
  • feat(LSTM): vanishing gradient + gradient clipping
  • ci: bump version to 3.0.4

neuralnetlib 3.0.3

09 Nov 16:07
746ecdf
Compare
Choose a tag to compare
  • perf: less memoryvore
  • ci: bump version to 3.0.2
  • Merge pull request #48 from marcpinet/perf-improve-lstm-attention
  • fix: evaluate new batch handling
  • docs: add method typing
  • fix(Dense): correct temporal data handling in forward and backward passes
  • ci: bump version to 3.0.3

neuralnetlib 3.0.2

07 Nov 01:31
e94dba0
Compare
Choose a tag to compare
  • perf: less memoryvore
  • ci: bump version to 3.0.2
  • Merge pull request #48 from marcpinet/perf-improve-lstm-attention

neuralnetlib 3.0.1

07 Nov 00:41
ac40d64
Compare
Choose a tag to compare
  • feat: improve rnn and add real life application
  • ci: bump version to 3.0.1
  • Merge pull request #47 from marcpinet/improve-rnn-and-real-life-application

neuralnetlib 3.0.0

06 Nov 23:12
4106a3d
Compare
Choose a tag to compare
  • docs: update decision boundary plot img
  • feat: add lstm and rnn support
  • feat: add attention
  • feat: improve attention
  • refactor: remove useless instructions
  • fix: some fixes and improvements
  • Merge pull request #46 from marcpinet/feat-add-lstm-rnn

neuralnetlib 2.9.0

23 Sep 00:28
3370f3b
Compare
Choose a tag to compare
  • feat: add history for fit method
  • fix: history jupyter cell
  • fix: earlystopping callback
  • refactor: more robust use of EarlyStopping
  • feat: made callbacks generic and more user friendly
  • ci: bump version to 2.9.0